Stat 1000 Distance: Assignment 3 Tips (Distance/Online Sections)

Published: Sat, 01/26/13


 
My tips for Assignment 3 are coming below, but first a couple of announcements.
 
Please note that my first two-day review seminar for Stat 1000 will be on Saturday, Feb. 2 and Sunday, Feb. 3, in room 100 St. Paul's College, from 9 am to 6 pm each day.  This seminar will cover the lessons in Volume 1 of my book.  
 
Please note that I am now taking registrations for my midterm exam prep seminars.  Please click this link for more info and to register, if you are interested:
Grant's Exam Prep Seminars 
 
Did you read my Tips on How to Do Well in this Course? 
Make sure you do:  Tips on How to Do Well in Stat 1000 
 
Did you read my Tips on what kind of calculator you should get?
Tips on what calculator to buy for Statistics
 
Did you miss my Tips for Assignment 2?
Tips for Stat 1000 Distance Assignment 2
 
If you are taking the course by Classroom Lecture (Sections A01, A02, etc.), I will send tips for Assignment 3 once it is posted.
 
Tips for Assignment 3 (Distance/Online Sections D01, D02, D03, etc.)
  
Don't have my book?  You can download a free sample containing Lesson 1 at my website here:
Grant's Tutoring Study Guides (Including Free Samples)
 
Study Lesson 4 in my study book (Density Curves and the Normal Distribution; in older editions of my book this is Lesson 2) to learn the concepts involved in Assignment 3.
 
To learn this lesson and do this assignment, you need Table A from the textbook.  That can be downloaded from the Resources section of Web Assign.  Here is a direct link to download this table:
Table A
 
Questions 1 and 2 are just like my questions 5 and 6 in Lesson 4.  Note, a cumulative proportion is a left area on the bell curve.  When they give you the cumulative proportion, they are merely giving your the area to the left of the z score.  You are being given the left area and asked to find the z-score.
 
Question 3 is a good run through of X-bell curve problems that I teach in the latter half of Lesson 4.  When they ask what score on the Reading Test is equivalent to Michael's Mathematics score, you will need to do some algebra.  First, you can determine Michael's z score for math.  Do not round that answer off, keep at lest four decimal places in your answer for the z score.  Since the reading score is equivalent, you know that this must also be Michael's z score for reading.  You can then use that z to work out the actual equivalent reading score.
 
Question 4
For the JMP part of the assignment, here are some tips:
Open a "New Data Table" in JMP.  Click the link to the data they provide in the question.  Press "Ctrl-A" to select all, or click and drag to select all the data.  Press "Ctrl-C" to copy it or right-click and select "Copy".  To paste the data into JMP, in the toolbar at top select "Edit" then "Paste with Column Names".  Double-click the "gpa" column heading and make sure the Data Type is Numeric and the Modeling Type is Continuous, using the drop-down menus to fix that if necessary.  Double-click the "sex" column heading and make sure the Data Type is Character and the Modeling Type is Nominal, using the drop-down menus to fix that if necessary.  Click OK.
 
To get side-by-side boxplots: In the toolbar at the top, select Analyze then select Fit Y By X.  In the pop-up menu, highlight the gpa column and click the "Y, Response" button.  Highlight the sex column and click the "X, Factor" button.  Click OK.  You will then see a graph with a vertical array of dots for the males (1) and the females (2).  If you do not get this graph, you did not follow my instructions above to confirm that "gpa" is numeric and continuous and "sex" is character and nominal.
 
Click the red triangle next to "Oneway Analysis ..." and select "Display Options".  You will then be able to select "Box Plots" in the Display Options sub-menu.  They don't ask you to, but I suggest you remove the Grand Mean line, so click the red triangle again and select Display Options and deselect Grand Mean.
 
You will need to copy and paste this output into a document to get ready to add the output from part (b) as well.  Here is how to do that:
 
Press "Alt" or click the thin blue line near the top of the window that has the boxplots to reveal the toolbar. Select the icon that looks like a fat white cross or plus sign "+".  This is your "Selection" tool.  Your mouse cursor should now have changed from an arrow to that white cross.  Click the title bar that says "Oneway Analysis ..." at the top of the output and that should select the entire output (boxplots, etc.).  Right-click and select Copy.
 
Now, open whatever program you use for word processing (such as Word).  In a new document, right-click and select Paste to paste your output into the document.
 
They also ask you to comment on the graphs.  I suggest you do this by adding a note to the document you have just pasted the output into.  Just type your comments below all the JMP stuff.  Compare the shape, centre and spread of the two boxplots.
 
Leave this document open, as you will need to paste the stuff from part (b) into it as well.
 
To get normal quantile plots: They want you to make a normal quantile plot for the males and a separate plot for the females.  In the toolbar at the top, select "Analyze" , then "Distribution".  In the pop-up menu, highlight "gpa" and click "Y, Column".  Highlight "sex" and click "By".  Click OK.  You now see separate histograms for the males and for the females.  Click the red triangle next to "gpa" for both the males and for the females, and select "Normal Quantile Plot" to get a separate normal quantile plot for the males and females.  Click the gray triangle (to the left of the red triangle) next to Quantiles and Summary Statistics to hide those outputs for both the males and females.
 
A normal quantile plot checks to see if a sample's distribution appears to be normal.  If the data follows a normal distribution, the normal quantile plot will look like a rising diagonal line.  If the plot looks curved rather than linear, there is evidence the data is not normal.  However, none of that seems to matter in your question, all they ask is which students are clear outliers, which, personally, I think is much easier to see from the points in your side-by-side boxplots than from your normal quantile plots.
 
Pretend you can see the outliers in the normal quantile plots, but really identify them from the boxplots above. I think it is quite clear which dots in your side-by-side boxplots are outliers.
 
Press "Alt" or click the thin blue line near the top of the window that has the normal quantile plots to reveal the toolbar. Select the icon that looks like a fat white cross or plus sign "+".  This is your "Selection" tool.  Your mouse cursor should now have changed from an arrow to that white cross.  You need to the graphs for both the females and males.  Click the title bar that says "Distributions sex=.." to select one of either the females or males output.  Right-click and select Copy. Paste it into the Word document you opened up in part (a).  Now return to the JMP output and select the other output and copy and paste it into the Word document.
 
Write a short note underneath these graphs identifying which scores are outliers.  You know very little according to the data table, so I suggest you just tell them the actual GPA you consider an outlier (there may be more than one), and if it is a male or female that has that GPA.  To assist you in identifying the actual GPA scores, you can sort the data table in order of ascending GPA.  To do so, in the data table, select "Tables" in the toolbar at top, and select "Sort".  In the "Sort-JMP" pop-up window, select "GPA" and click "By" and click OK.  You will then be shown a new data table with the data sorted in order of ascending GPA.  You can now easily read off the smallest and largest GPAs and list the ones you consider outliers according to the side-by-side boxplots you made in part (a).
 
You can now save this Word file as a PDF and upload it into your assignment.